Sticks and stones may break my bones, but words will never hurt me. This was a mantra I picked up on the playground at elementary school--something I repeated over and over again anytime I came face to face with racism. It was a coping mechanism meant to guard my heart from the cacophony of discriminatory comments that shaped me as a young Korean American girl growing up in predominantly white spaces. But now that I'm well into adulthood, I think about the girls of color who are also being taught to pretend that words don't hurt--and the people this way of thinking actually protects. It's hard to escape the unrelenting consequences of racism: In the past year alone, we lost Breonna Taylor, George Floyd, Ahmaud Arbery, and the six women of Asian descent murdered in Atlanta (Xiaojie "Emily" Tan, Daoyou Feng, Suncha Kim, Yong Ae Yue, Soon Chung Park, Hyun Jung Grant) at the hands of this insidious disease--and those are just the names that were in the headlines. If we don't acknowledge ...

In recent years, we have seen many products being created with increasing participation of Artificial Intelligence (AI), Machine Learning, and other wild cards that compose the last decade's frenzy: Data Science. In this field, the acronym MLUX circulates around the world and refers to Machine Learning User Experience, a path of no return. Products that can guess when you are leaving home, what you would like to eat, what is the best route to get to work and et cetera; instigate practical, ethical, and methodological questions. It doesn't take a truckload of information to understand this, just good examples of content are enough to illustrate how Research (with a capital "R" and everything!) in technology, especially UX, has exchanged insights and data with machines that learn while we use them. Good examples start with an AI Designer (or artificial intelligence designer), another design buddy from startups immersed in Data Science.

This paper studies the complexity for finding approximate stationary points of nonconvex-strongly-concave (NC-SC) smooth minimax problems, in both general and averaged smooth finite-sum settings. We establish nontrivial lower complexity bounds of $\Omega(\sqrt{\kappa}\Delta L\epsilon^{-2})$ and $\Omega(n+\sqrt{n\kappa}\Delta L\epsilon^{-2})$ for the two settings, respectively, where $\kappa$ is the condition number, $L$ is the smoothness constant, and $\Delta$ is the initial gap. Our result reveals substantial gaps between these limits and best-known upper bounds in the literature. To close these gaps, we introduce a generic acceleration scheme that deploys existing gradient-based methods to solve a sequence of crafted strongly-convex-strongly-concave subproblems. In the general setting, the complexity of our proposed algorithm nearly matches the lower bound; in particular, it removes an additional poly-logarithmic dependence on accuracy present in previous works. In the averaged smooth finite-sum setting, our proposed algorithm improves over previous algorithms by providing a nearly-tight dependence on the condition number.

We investigate the addition of constraints on the function image and its derivatives for the incorporation of prior knowledge in symbolic regression. The approach is called shape-constrained symbolic regression and allows us to enforce e.g. monotonicity of the function over selected inputs. The aim is to find models which conform to expected behaviour and which have improved extrapolation capabilities. We demonstrate the feasibility of the idea and propose and compare two evolutionary algorithms for shape-constrained symbolic regression: i) an extension of tree-based genetic programming which discards infeasible solutions in the selection step, and ii) a two population evolutionary algorithm that separates the feasible from the infeasible solutions. In both algorithms we use interval arithmetic to approximate bounds for models and their partial derivatives. The algorithms are tested on a set of 19 synthetic and four real-world regression problems. Both algorithms are able to identify models which conform to shape constraints which is not the case for the unmodified symbolic regression algorithms. However, the predictive accuracy of models with constraints is worse on the training set and the test set. Shape-constrained polynomial regression produces the best results for the test set but also significantly larger models.

This paper addresses the problem of robotic operations in the presence of adversarial forces. We presents a complete framework for survey operations: waypoint generation,modelling of forces and tuning the control. In many applications of environmental monitoring, search and exploration, and bathymetric mapping, the vehicle has to traverse in straight lines parallel to each other, ensuring there are no gaps and no redundant coverage. During operations with an Autonomous Surface Vehicle (ASV) however, the presence of wind and/or currents produces external forces acting on the vehicle which quite often divert it from its intended path. Similar issues have been encountered during aerial or underwater operations. By measuring these phenomena, wind and current, and modelling their impact on the vessel, actions can be taken to alleviate their effect and ensure the correct trajectory is followed.

Seeking the equivalent entities among multi-source Knowledge Graphs (KGs) is the pivotal step to KGs integration, also known as \emph{entity alignment} (EA). However, most existing EA methods are inefficient and poor in scalability. A recent summary points out that some of them even require several days to deal with a dataset containing 200,000 nodes (DWY100K). We believe over-complex graph encoder and inefficient negative sampling strategy are the two main reasons. In this paper, we propose a novel KG encoder -- Dual Attention Matching Network (Dual-AMN), which not only models both intra-graph and cross-graph information smartly, but also greatly reduces computational complexity. Furthermore, we propose the Normalized Hard Sample Mining Loss to smoothly select hard negative samples with reduced loss shift. The experimental results on widely used public datasets indicate that our method achieves both high accuracy and high efficiency. On DWY100K, the whole running process of our method could be finished in 1,100 seconds, at least 10* faster than previous work. The performances of our method also outperform previous works across all datasets, where Hits@1 and MRR have been improved from 6% to 13%.

This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of \cite{dosovitskiy2020image} for encoding high-resolution images using two techniques. The first is the multi-scale model structure, which provides image encodings at multiple scales with manageable computational cost. The second is the attention mechanism of vision Longformer, which is a variant of Longformer \cite{beltagy2020longformer}, originally developed for natural language processing, and achieves a linear complexity w.r.t. the number of input tokens. A comprehensive empirical study shows that the new ViT significantly outperforms several strong baselines, including the existing ViT models and their ResNet counterparts, and the Pyramid Vision Transformer from a concurrent work \cite{wang2021pyramid}, on a range of vision tasks, including image classification, object detection, and segmentation. The models and source code used in this study will be released to public soon.

The NeurIPS 2020 Procgen Competition was designed as a centralized benchmark with clearly defined tasks for measuring Sample Efficiency and Generalization in Reinforcement Learning. Generalization remains one of the most fundamental challenges in deep reinforcement learning, and yet we do not have enough benchmarks to measure the progress of the community on Generalization in Reinforcement Learning. We present the design of a centralized benchmark for Reinforcement Learning which can help measure Sample Efficiency and Generalization in Reinforcement Learning by doing end to end evaluation of the training and rollout phases of thousands of user submitted code bases in a scalable way. We designed the benchmark on top of the already existing Procgen Benchmark by defining clear tasks and standardizing the end to end evaluation setups. The design aims to maximize the flexibility available for researchers who wish to design future iterations of such benchmarks, and yet imposes necessary practical constraints to allow for a system like this to scale. This paper presents the competition setup and the details and analysis of the top solutions identified through this setup in context of 2020 iteration of the competition at NeurIPS.

ABSTRACT Regional rainfall forecasting is an important issue in hydrology and meteorology. This paper aims to design an integrated tool by applying various machine learning algorithms, especially the state-of-the-art deep learning algorithms including Deep Neural Network, Wide Neural Network, Deep and Wide Neural Network, Reservoir Computing, Long Short Term Memory, Support Vector Machine, K-Nearest Neighbor for forecasting regional precipitations over different catchments in Upstate New York. Through the experimental results and the comparison among machine learning models including classification and regression, we find that KNN is an outstanding model over other models to handle the uncertainty in the precipitation data. The data normalization methods such as ZScore and MinMax are also evaluated and discussed. Keywords: rainfall forecasting, k-nearest neighbor, deep and wide neural network, reservoir computing, long short term memory. 1 INTRODUCTION New York historically had sufficient precipitation until recently, with intense drought occurring over the 2016 growing season, especially in western New York (Todaro 2018). The observed precipitation in 2016 was less than normal, with shortfalls of 4-8 inches being common in the 90 days leading up to the drought watch. Accurate rainfall forecasting is important for planning in agriculture and other relevant activities. Although a number of modern algorithms and applications have been used to forecast rainfall, there are two categories of approaches to solve the problem. However, it is thought not feasible limited by the complex climatic system in various spatial and temporal dimensions. A second category is based on the data mining and pattern recognition, which attempts to mine rainfall patterns and learn the knowledge from numerous features and a large volume of data. Historical meteorological data including precipitation data are used to feed and train the recognition model and further predict the evolution of other storms.

Competitive board games have provided a rich and diverse testbed for artificial intelligence. This paper contends that collaborative board games pose a different challenge to artificial intelligence as it must balance short-term risk mitigation with long-term winning strategies. Collaborative board games task all players to coordinate their different powers or pool their resources to overcome an escalating challenge posed by the board and a stochastic ruleset. This paper focuses on the exemplary collaborative board game Pandemic and presents a rolling horizon evolutionary algorithm designed specifically for this game. The complex way in which the Pandemic game state changes in a stochastic but predictable way required a number of specially designed forward models, macro-action representations for decision-making, and repair functions for the genetic operations of the evolutionary algorithm. Variants of the algorithm which explore optimistic versus pessimistic game state evaluations, different mutation rates and event horizons are compared against a baseline hierarchical policy agent. Results show that an evolutionary approach via short-horizon rollouts can better account for the future dangers that the board may introduce, and guard against them. Results highlight the types of challenges that collaborative board games pose to artificial intelligence, especially for handling multi-player collaboration interactions.